Wireless Speech Recognition ..

Sennheiser ME 3, from eMicrophones

2010-05-03T09:13:00.000-07:00

Our hat is off to eMicrophones.com for their Sennheiser ME 3 Headset Microphone, manufactured exclusively for eMicrophones by Sennheiser.

The ME 3 has received raving reviews from users worldwide, both for musical use, speech applications and in all scenarios where superb performance and noise-canceling are a prerequisite.

Here's a quick video about the ME 3 from eMicrophones..

If you are seeking a superior microphone with unparalleled support from it's vendor, the Sennheiser ME 3 from eMicrophones.com is a best bet!

Robotic tongues improving speech recognition..

2008-07-30T14:28:00.000-07:00

The article we found today, can be read here.

But, the video below kind of "tells the story"!

Pretty cool... Eh?

Now there is voice dial for the iPhone!

2008-07-29T18:03:00.000-07:00

A company named "Makayama" has released a voice dial for the iPhone, with interesting features..

Record voice samples for any address book contact - speak to dial it's number.

It's multilingual, and semi-trainable.

Here's the YouTube video:

It's received rather glowing reviews from Engadget & Gizmodo, who can both be tough to impress.

The manufacturer's article can be read here.

Google + speech-recognition indexing of videos!

2008-07-15T21:37:00.000-07:00

Google is now utilizing speech recognition indexing of the spoken audio in videos! Users you can search for spoken text in a video, but for now, only in selected videos only (Political Videos).

Check out the new feature by adding the Google Election Video Search Gadget to your iGoogle page, or view the gadget on their as a standalone page. The gadget works by adding little yellow markers to the timeline letting you know where the word occurs.

Google isn't the first site to combine speech recognition with video search. Blinkx and EveryZing offer the services; But now that the 800 pound gorilla has entered the online video spoken audio search world - look for this market to evolve quickly, and our bet is on Google for leading the pack, of course.

A how-to/helpful "Space" you really should visit..

2008-06-25T18:49:00.000-07:00

We won't waste any ink on the Windows Live Space referenced here;
It has to be visited to be understood.
But be assured it's not a complicated, ugly/busy site that's cryptic in its content.

If you have any inclination, now or soon, to begin using the ultra-powerful
Macros for Windows Speech Recognition you must visit this website... !!

Windows Speech Recognition Macros

ENJOY!

A speech-driven PIM on steroids, from Speereo!

2008-06-25T05:22:00.000-07:00

Speereo's PR Manager, who left a kind comment to our last posting about their super-cool Voice Translator has alerted us to another product, titled "Sapie", which has received rather glowing reviews by 3rd parties.

We haven't tested it yet, but here is a pretty comprehensive overview/review of Sapie, that is well worth reading.

In the meantime.. Take a look at this performance comparison chart!

We hope to be speaking with Speereo's PR Manager, Gleb Klimshin fairly soon and he's promised to discuuss some Wireless Speech Programs they've developed..If they are up to par with Speereo's other products..

National Instruments - programming w/ speech!

2008-06-21T20:46:00.000-07:00

National Instruments "LabVIEW Real-Time Modules", that develop reliable and deterministic applications deployed to a variety of scalable hardware targets is vigorously now using Windows Speech Recognition ("WSR") to both program and test their development.

A video is worth a few thousand words:
Click here to see a very interesting demonstration...!!

Nuance vs Vlingo - threatens Yahoo Voice Search?

2008-06-18T12:48:00.000-07:00

Via XEconomy, today;

"If a Texas district court grants an injunction sought by Burlington, MA-based Nuance Communications (NASDAQ: NUAN), it could force Yahoo to shut down the voice-enabled version of its mobile search platform. The search tool is powered by software from Vlingo, a Cambridge, MA-based startup Nuance sued yesterday for alleged patent infringement.

The Yahoo (NASDAQ: YHOO) platform, called oneSearch with Voice, works on Blackberry Pearl, Blackberry Curve, and Blackberry 8800 series smartphones, and allows users to enter Web search queries such as “Boston Red Sox scores” or “United Airlines Flight 541″ simply by speaking them into the device. Vlingo’s deal to get its speech recognition technology included in oneSearch was seen as a major coup for the Harvard Square startup, which has about 35 employees and recently closed a $20 million Series B financing round led by Yahoo.

Nuance filed its lawsuit in the United States District Court for the Eastern District of Texas, a jurisdiction famous for favoring plaintiffs in patent-infringement cases. Xconomy obtained a copy of Nuance’s complaint. It alleges that Vlingo’s speech recognition software—including “without limitation, products and services Vlingo is supplying to Yahoo! oneSearch”—infringes on U.S. Patent No. 6,766,295, which was issued to Nuance engineers Hy Murviet and Ashvin Kannan in 2004. The patent covers a technique for making computerized transcription of a users’ speech more accurate over time using audio samples from multiple sessions such as phone calls.

The suit seeks unspecified monetary damages and attorney fees, and also asks the court to “preliminarily and permanently restrain” Vlingo and its business partners from making, using, and selling the allegedly infringing software. Those partners would presumably include Yahoo's 'one search with Voice' platform."

Speech Analytics - an evolving business resource..

2008-06-11T19:39:00.000-07:00

Speech analytics technology has evolved in recent years, providing organizations with insight into sales, service and products gleaned from the voice biometrics of customers.

It has also brought a dilemma for organizations deploying it - Does it belong under the hands-on management of the contact center? Or should marketing govern its use? Or maybe it should remain under the strict control of Business Intelligence (BI)?

An important question organizations need to consider when they're purchasing speech analytics tools, according to Keith Dawson, senior analyst with Frost and Sullivan.

"There is no one way to determine which is best -- different options are good at different points," Dawson said. "A lot of it is going to depend on where the purchaser's analytics culture is."

Vendors that have developed speech analytics typically promote just the core speech analytics functions; Parsing recordings for meanings, establishing patterns and alerting users to unseen connections; but there are actually three primary philosophies for organizations purchasing speech analytics.

Businesses with entrenched speech technology in self service or other speech-recognition tools might take the "what's it doing re: in-house performance" approach.

In the contact center environment, agent performance optimization vendors are pushing the technology from the workforce optimization side. Speech analytics are a way to both measure agent skills, and train them as well.

When presented as a marketing tool/revenue producer, discussions on buying speech analytics turns from cost cutting to profits.
Contact center mangement has often concentrated only on cost control;
Average Handle Time ("AHT") or per-call Average Work Time ("AWT");
and have mostly ignored profit and revenue.

|
"They're going to have to collaborate with business people who don't care about the activities & performance inside the call center -- they care only about the outcomes," Dawson said.

The most remote speech-driven system yet?

2008-06-10T17:43:00.000-07:00

On Bantayan Island in the Philippines, to prove its new speech-driven services work, the Government Service Insurance System (GSIS) unveiled a remote voice biometrics (a/k/a "voice recognition") system for its members on a picturesque island located in the northernmost tip of Cebu.

"If it will work in Bantayan Island, it will work anywhere," said GSIS President and General Manager Winston Garcia, in a briefing here. Garcia said the service is being launched as part of its modernization program. "This system removes the need for them to go to a GSIS office to renew their pension status. They can now do so remotely, via a phone call," noted Garcia, explaining how the system is intended to reduce large inbound call queues into GSIS offices.

The service was beta-tested in the United States prior to the local (Cebu) launch; E.G. Washington, New York, Chicago, Los Angeles, San Francisco, and Hawaii.

The speech driven "GSIS Voice Activated Processing System" (G-VAPS) enables its 1.2 million members to transact with the GSIS using their unique voice as their "electronic signature,". The system is secure, and is be able to detect "tape-recorded" as opposed to live speech. Active members and pensioners call a US-based GSIS Teleservice toll free number to use the service.

Currently, it allows members to apply for and process loans. It can also be initially used by pensioners to renew their status to active members; Active members can then go to GSIS office to record their voice after presenting proper identities.

"This is voluntary but it provides them convenience," said Garcia when asked if he expects all members to avail of this new service. He also noted GSIS Wireless Automated Processing System kiosks remain another option to apply for loans.

Garcia further noted the system was customized by its own information technology department.

Speech recognition's "mainstream", in unusual fields

2008-06-07T09:12:00.001-07:00

Cited primarily from an article at http://computer.getmash.net/;

Speech recognition has long languished in the no-man’s land between sci-fi fantasy (”Computer, engage warp drive!”) and everyday usage reality.

But that’s changing fast, as advances in computing power, artificial intelligence, powerful API's & newly available WSR Macros, make speech recognition the next powerful step for everyday use by "non-geek" users, user-interface design and now electronic voice-based security.

As to voice-based security: A whole host of highly advanced speech technologies, including emotion and lie detection, are moving from the lab to the marketplace.

This not a new technology,” says Daniel Hong, an analyst at Datamonitor who specializes in speech technology. “But it took a long time for Moore’s Law to make it viable.”

Mr. Hong estimates at the speech technology market is worth more than $2 billion, with plenty of growth in embedded and network apps.

And it’s about time. Speech recognition's technology has been around since the 1950s, but only recently have computer processors and accompanying artificial intelligence become powerful enough to handle the complex algorithms required to recognize our speech, both local & remote, improve our lives & productivity, and open our eyes to the long tail of speech recognition fields.

A few examples:
There are already several capable voice-controlled technologies on the market. You can issue spoken commands to devices like Motorola’s Mobile TV DH01n, a mobile TV with navigation capabilities, and a host of telematics GPS devices. Microsoft recently announced a deal to slip voice-activation software into cars manufactured by Hyundai and Kia, and its TellMe division is investigating voice-recognition applications for the iPhone. And Indesit, Europe’s second-largest home appliances manufacturer, just introduced the world’s first voice-controlled oven.

Yet as promising as this year’s crop of specch-controlled devices are, they’re just the beginning.

Speech technology comes in several flavors, including the speech recognition that drives voice-activated mobile devices; network systems that power IVR's using automated speech recognition, the unequalled desktop Vista Speech recognition, now with available macros {which we use to post & write articles) and the long-standing the standard in the Healthcare industry, the highly impressive network-based Philips SpeechMagic systems.

Voice biometrics (the true technical description of the often mis-used phrase "voice recognition") is a particularly hot area. Every individual has a unique voice print that is determined by the physical characteristics of his or her vocal tract. By analyzing speech samples for telltale acoustic features, voice biometrics can verify a speaker’s identity either in person or over the phone, without the specialized hardware required for fingerprint or retinal scanning.

The technology can also have unanticipated consequences. When the Australian social services agency Centrelink began using voice biometrics to authenticate users of its automated phone system, the software started to identify welfare fraudsters who were claiming multiple benefits — something a simple password system could never do.

The Federal Financial Institutions Examination Council has issued guidance requiring stronger security than simple ID and password combinations, which is expected to drive widespread adoption of voice verification by U.S. financial institutions in coming years. Ameritrade, Volkswagen and European banking giant ABN AMRO all employ voice-authentication systems already.

Advanced voice-recognition systems that can tell if a speaker is agitated, anxious or lying are also in the pipeline.

Computer scientists (e.g. at Carnegie Mellon) have already developed software that can identify emotional states and even truthfulness by analyzing acoustic features like pitch and intensity, and lexical ones like the use of contractions and particular parts of speech. And they are honing their algorithms using the massive amounts of real-world speech data collected by call centers and free 411 speech-driven services such as the extremely popular Goog411.

A reliable, speech-based lie detector would be a boon to law enforcement and the military. But broader emotion detection could be useful as well. Our host company which developed the now-standard Law Enforcement "Mobile Prosecutor" is presently experimenting with embedding it with voice-stress analysis.

In another example, a virtual call center agent that could sense a customer’s mounting frustration and route her to a live agent would save time, money and customer loyalty.

“It’s not quite ready, but it’s coming pretty soon,” says James Larson, an independent speech application consultant who co-chairs the W3C Voice Browser Working Group.

Companies like Autonomy eTalk claim to have functioning anger and frustration detection systems already, but experts are skeptical. According to Julia Hirschberg, a computer scientist at Columbia University, “The systems in place are typically not ones that have been scientifically tested.”

According to Hirschberg, lab-grade systems are currently able to detect anger with accuracy rates in “the mid-70s to the low 80s.”

They are even better at detecting uncertainty, which could be helpful in automated training contexts. (Imagine a computer-based tutorial that was sufficiently savvy to drill you in areas you seemed unsure of.)

Lie detection via voice stress & syntax-pattern deviation analysis is a tougher nut to crack, but progress is being made.

In a study funded by the National Science Foundation and the Department of Homeland Security, Hirschberg and several colleagues used software tools developed by SRI to scan statements that were known to be either true or false. Scanning for 250 different acoustic and lexical cues, “We were getting accuracy maybe around the mid- to upper-60s,” she says.

That may not sound so hot, but it’s a lot better than the commercial speech-based lie detection systems currently on the market. According to independent researchers, such “voice stress analysis” systems are no more reliable than a coin-toss.

It may be awhile before industrial-strength emotion and lie detection come to a call center near you. But make no mistake: They are just around the proverbial corner. And they will be preceded by a mounting tide of gadgets that you can talk to, argue with and intelligently discuss topics with.

Don’t be surprised if, some day soon, your Bluetooth headset tells you to calm down. Or informs you that your last caller was lying through his teeth.

Now that Windows Speech Recognition Macros for Windows Vista™ are in feverish development, both in-house (Microsoft Speech Components Group [ listen_+at+_microsoft.com ], and the beta group inside the Microsoft Speech Yahoo Technical Group) - desktop speech recognition is advancing daily by leaps and bounds, literally.

Powerful WSR macros that can, for example:

Open e-mail messages from a specific (non-Inbox) account with TO: / CC: / BCC: and Subject: fields already completed;

Macros that can move large blocks of extant text in and out of specific locations inside different applications;

Navigate & move items in and out of various folders inside Vista Explorer;

Spoken database lookups

are already evolving and being used & improved daily. It will not be long before speech recognition becomes "what we just use" for most of our daily work & living activities..

(A detailed post on the powerful new WSR Macro Tool & evolving macros is coming soon; We're gathering data, useful macros and research to be sure it is both interesting & useful to all types of speech recognition users)

Remote speech recognition, with Instinct!

2008-06-05T19:42:00.000-07:00

Samsung's "Instinct" mobile device, scheduled to become available June 20th, now includes some rather advanced speech recognition coupled with nice artificial intelligence features. Slated to be a viable i-Phone competitor, this feature certainly helps that "battle", IOHO.

Via Gizmodo's very nice article:
"Samsung's Instinct may be the best stab at the coveted title of iPhone killah this CTIA. The 3.1-inch touchscreen phone has localized haptic feedback, plus three hard navigation keys.

Check out the well-done You Tube video:

Let's hope the Instinct turns out to be all it's promised.. This advanced speech recognition should really begin to galvanize widespread recognition of true remote speech recognition, from newly arriving moble devices!

Speech-Recognition, translation style!

2008-06-04T11:46:00.000-07:00

Speereo, a leading developer for voice recognition software offers a new "Free UEFA Euro 2008 Guide" complete with its popular application called Speereo Voice Translator.

Speereo Voice Translator is a perfect solution for travelers and understands every spoken word. Once the user pronounces a phrase in his native language, Speereo Voice Translator immediately reads back the same phrase in one of 14 languages included into an application. It is designed for devices that have Windows Mobile (Pocket PC and Smartphones) or Symbian OS installed.

Via the Speereo web page:
"Speereo Voice Translator is available in two versions: multilanguage and two language. Multilanguage version of Speereo Voice Translator for business communication and traveling, running on smartphones and Pocket PCs, is an innovative phrasebook that provides translation among 14 languages: English, Spanish, German, French, Italian, Russian, Chinese Simplified, Chinese Traditional, Turkish, Portuguese, Korean, Japanese, formal Arabic, Finnish"

It seems speech recognition becomes more ubiquitous.. every week!

Adobe Releases Speech-Recognition Indexing

2008-05-27T13:23:00.000-07:00

Via several non-official Adobe-centered blogs and news articles, Adobe has released a Soundbooth Beta that showcases a host of new features, including new speech recognition technology that lets users create transcripts of dialogue tracks quickly and search them for words and phrases across their timeline.

Adobe hasn't yet published any official press releases, so this feature may be a tad undocumented and in early beta form to date.

They also have not disclosed which engine they are using (if it's not propreitary) to parse spoken audio tracks for speech recognition indexing.

We've blogged about the two most popular such engines, Everyzing's "Ramp" and it's predecessor and core technology, MIT's "Lecture Browser" from CSAIL (Computer Science and Artificial Intelligence Laboratory) and it's very likely this indexing uses these platforms or variations thereof (IOHO), although new "automated indexing of video's spoken audio" technology is emerging from several new entities, including IBM.

Tweet by phone.. TwitterFone!

2008-05-07T15:17:00.000-07:00

Yes, it's true.. Now you can Tweet by phone.

We didn't get an invite yet, but we'll be sure to post more when we do..

SPEAK: Speech-enabled auto attendant for SMB's!

2008-05-06T20:14:00.000-07:00

Active Voice has rolled out a turnkey speech enabled auto-attendant that's priced and aimed at small to mid-sized business markets, named "SPEAK".

Via the press release & web page:
"The engineering framework of SPEAK is designed to be a sophisticated turnkey solution that is considerably more affordable, while being easy to implement, easy to deploy and easy to use. Thus, SPEAK provides SMBs a practical solution for speech attendant, corporate directory as well as mobility access."

Some productivity features the maker notes:

Upgrades customer service while reducing “zero-out” calls

Eliminates the push button frustration as well as the need to search for numbers

Provides total 24/7/365 self-service information such as employee and department directories, company information, driving directions, business hours, etc.

Performs dynamic call routing to ensure all incoming callers are treated in a personalized and professional manner

Frees front desk support to deal with important face-to-face matters

Keeps mobile workforces connected efficiently and provides hands-free access for safety

Reduces the need for maintaining and printing company directories

Secures access to your telephony resources across all networks

Per Eyal Inbar, General Manager of Marketing and Product Development:
"Active Voice SPEAK leverages LumenVox's cutting-edge Speech Engine and Digium's open standard hardware, enabling SPEAK to be offered at a price point that is unbeatable in the market and at a level of sophistication that is yet to be experienced by SMBs. The bottom line of SPEAK is simplicity, affordability and ease of use."

Plug-n-Play medical speech recognition from Dolbey

2008-05-05T16:43:00.000-07:00

Dolbey has announced the release of "Voice2Text" (powered by Royal Philips Electronics); the first medical speech recognition transcription system that allows medical customers to keep their existing document platform!

Via the Dolbey PDF product sheet:
"Voice2Text is unique in that the speech recognition has been integrated with Dolbey’s Fusion Voice digital dictation system and provides simple, yet functional integration to a company’s existing document platform."

Voice2Text is unique in yet another area;
"This non-invasive approach to applying back-end speech is uniquely being offered in a pay-as-you-go model to minimize upfront investment"(Dolbey's Product PDF).

It's certainly exciting to see these recent advances in speech recognition, particularly as they become simpler and more effective..

Speech recognition grows by 100% in the military

2008-05-05T08:06:00.000-07:00

According to a Businesswire.com article today;
Nuance's Dragon NaturallySpeaking® Medical software has seen a one hundred percent growth over the last year.

Via the businesswire.com article;
"Dragon Medical has extended its value into the Federal government through its seamless integration with AHLTA, the military’s electronic health record, to enable clinical documentation through accurate voice-to-text speech recognition. According to a survey performed across 17 distinct Army, Navy, Air Force and Marine Corps medical treatment facilities, 79.9 percent of those surveyed chose Dragon Medical as their preferred method for documenting care within AHLTA."

Craig Rohan, Staff Pediatrician at the Peterson Air Force base in Colorado is quoted as saying:
“Speech recognition technology allows for more thorough and expedited documentation of our patient encounters. Since using Dragon Medical I find that medical statements are more easily captured during routine clinic workflow. The comprehensive medical vocabulary Dragon Medical works off of ensures that the symptoms or diagnosis we say are correctly documented”
and
“More advanced users of Dragon Medical can take advantage of features such as 'macros', 'shortcuts' and other tools that further streamline documentation by producing a partially, or in some cases fully populated medical record when prompted by the command ‘normal study,’ for example. We’ve seen significant productivity improvements across those who have embraced speech recognition to document care.”

President Bush has set a goal for Americans to have an electronic health record by 2014. The DOD began AHLTA; an always available electronic health record for all active military, retirees and their families and expects to have it fully implemented by 2011.

A comment about Fujitsu's DSR from a reader

2008-04-30T07:52:00.000-07:00

It's no secret we are propnents of Distributed Speech Recognition (DSR), and one of our readers posted an encouraging comment about the NTT DoCoMo F884i..

The comment from Mike:
"I spoke to President (and soon chairman) Suzuki of Advanced Media last week about DSR and the handset by Fujitsu uses the Fujitsu/AM DSR and not the ETSI Standard that has been implemented on other DoCoMo 905i series phones and all future FOMA phones in Japan. Very nifty indeed!"

It's great news to hear that DSR is gaining well deserved footholds!

Garmin's nuvi 880 gets great recognition!

2008-04-30T07:19:00.000-07:00

The Garmin nuvi 880, the first navigation unit with full bragging rights to great speech recognition has garnered some glowing reviews from various websites.

One particular review by PC Magazine's Craig Ellison gives some detailed results from a former Dragon speech recognition user, and all in all, our hats are off to a great product with real speech recognition!

More speech recognition enabled robots..

2008-04-21T01:59:00.000-07:00

The original REEM-A and the new REEM-B, being shown for the 1st time in Abu Dhabi April, 2008 offers speech recognition as well as other advanced robotic features! {Speech recognition featured in the last segments below}

More from the manufacturer can be read here

Microsoft's new Response Point partners..

2008-04-20T15:17:00.000-07:00

It's been sort of a "slow" week for speech recognition, but yesterday Microsoft announced (2) new SIP Partners for their cool new Response Point, speech recognition-enabled software-based PBX.

The two firms, Cbeyond and New Global Telecom (NGT) will provide SIP services for the Microsoft Response Point digital voice/IP-VoIP PBX phone systems designed for for small businesses.

After completing extensive interoperability testing, NGT became the first certified, Microsoft recommended service provider offering industry-standard SIP phone services that work superbly with the Response Point systems.

CBeyond and NGT were selected as partners because of their nationwide coverage, high quality of voice service, and customer satisfaction. Each service provider will roll out unique partner programs for VARs to boost their ability to reach and service small businesses with Response Point.

EveryZing rolls out RAMP

2008-04-14T10:53:00.000-07:00

EveryZing, a leader in the new technology of indexing the spoken audio inside video clips,today announces RAMP (Reach, Access, Monetization and Protection) that gives media companies control over how their content is discovered, distributed, presented and consumed.

For those who don't know about EveryZing's technology:
Via EzeryZing's website:

"EveryZing’s patented speech-to-text technology wraps every piece of audio and video from your site in a rich layer of metadata, including a full text output of the spoken word track."

and

"At the heart of EveryZing’s solutions is our core speech-to-text technology – the fruit of $100 million of government-funded research by BBN Technologies (inventor of the internet’s ubiquitous “@” symbol). EveryZing’s speech-to-text technology enables multimedia clips to be robustly indexed, increasing their “discoverability” by the web search engines and boosting online advertising opportunities. EveryZing uses its technology to ensure that every piece of audio and video from each client’s web site is wrapped in a rich layer of metadata, including a full text output of the spoken word track, so it can be searched and accessed easily and precisely by consumers, just like text… and, as a result, online advertisers can now place contextually relevant messages within and along side multimedia content, just like text."

More on RAMP, via their website:

"RAMP is EveryZing’s point-and-click web multimedia management console, giving you control over your content, context and brand. RAMP makes it easy for “infotainment” web site operators to control every aspect of the audio and video content on your site – from full-text indexing the clips, to publishing them in any format you choose, to monitoring visitor traffic. RAMP ensures reach, access, monetization and protection of your online audio and video.

Based in Cambridge, Mass., EveryZing is a pioneer in next-generation universal search technology and video search engine optimization (video SEO). EveryZing was originally founded by BBN Technologies, creators of the email @ symbol. The company’s core intellectual property and capabilities include speech-to-text technology and natural language processing.

EveryZing's automated speech recognition is impressive, to say the least; It even outputs line-by-line transcriptions. We've blogged about them before, and they continue to impress us as their technoloy evolves.

DoCoMo's new handset; built-in speech recognition

2008-04-14T06:48:00.000-07:00

Japan's NTT DoCoMo Inc (NYSE: DCM) is releasing the FOMA "Raku-Raku Phone Premium" F884i mobile phone today, with built-in speech recognition for remote transcription of email text.

The handset, made by Fujitsu Ltd, contains new & proprietary technology to enter e-mail text using remote speech recognition. If the "voice input" button in the e-mail editing display is pressed, software that extracts the characteristics of the user's speech (and performs Analog-to-Digital conversion) will start, and access the DoCoMo's i-mode site.

When users say what they want transcribed into an email, the in-box software sends the dictation to the i-mode server. There, speech recognition software manufactured by Advanced Media Inc outputs transcribed text. The F884i receives the transcribed text, displays it in the email's text display interface.

As best we can tell, without a direct response from DoCoMo or Advanced Media - This appears to be DSR (Distributed Speech Recognition) which we've blogged about in the past; and we are tremendous fans of DSR as a global answer to near-perfect mobile speech recognition.

We've also emailed David Pearce, founder and Chief Developer of this emerging technology to see if he has any information on whether this may, in fact be DSR..
Check back later for details!

Pioneer's LINC releases, with "intent" recognition

2008-04-13T12:42:00.000-07:00

Pioneer's Mobile Entertainment Division (Long Beach, Ca.) is releasing the promised AVIC-F500BT LINC (Lifestyle Innovation Network Console), a portable navigation and speech recognition unit.

The LINC's main function: An in-dash GPS device with 1.2 million points of interest, an SD slot and it uses MSN for traffic, weather and gas price updates.

What's cool is the device incorporates Pioneer's "VoiceBox Conversational Voice Search Platform," a nicely developed speech recognition system that enables iPod or other MP3 players and voice control for you Bluetooth-connected phone.

VoiceBox's innovation is it's extraction algorihm that allow what Pioneer terms "conversational commands" and "intent recognition", and very advanced noise-canceling that deals quite well with ambient vehicle noise and the presence of extra voices.

The conversational element is its ability to deduce various forms of basic commands. "I want to hear the artist Herbie Hancock" or "Play Herbie Hancock" will produce the same result.
(** The LINC offers iPod-specific playback recognitions such as album name, playlist name or music genre.)

Pioneer's "conversational recognition" spreads it's wings with the ability to extract a relevant phrase from a inside a long utterance, that contains irrelevant words: "Uhh, play, hmm, let's see, that album Abbey Road". The unit has the capacity to ignore extra words it decides are superflous.

Pioneer's "Intent Recognition" is a artificial intelligence that reponds at a higher level to enhance the user's interactive abilities. With typical command & control, pre-defined, specific commands like "Call Phil Donnahue at home" or "Call Georg Bush on the mobile phone" are prerequisite. Pioneer's AI prompts for additional information, if it appears necessary for a positive recognition; E.G. "I have 2 numbers for James Caan - Home and Mobile. Which one would you like to call?"

An excellenc cnet.com video from CES 2008, of the LINC can be seen here.

Speech recognition moves into Flight Simulators

2008-04-10T05:54:00.000-07:00

As of March 7th, the flight simulation game add-in First Officer released. First Officer is 100% command& control speech recognition, complete with a training interface, and spoken confirmation of commands!.

Via their website:
"Gone are the days of having to read 45 minutes of text to a computer; speech
recognition technology has come a long way in the last 5 years.
Lengthy speech recognition training is no longer required and individual
commands can be trained when needed."

A terrific blog about digital dictation..

2008-04-09T19:40:00.000-07:00

We've received a comment from the bloggers at the Acappella Conference Audio Recorder Blog, to our recent post about Sony's new henheld recorders..

We visited their site, and were quite impressed with both the quality and quantity of the information we found there. Their apparent sponsors, Acappella, seem to have an impressive digital recorder, that even integrates with SharePoint!

Their website offers an extremely well-written & researched whitepaper.

Their Technology page notes that the Acappella digital recorder supports:

- Integration into many popular digital dictation packages

- Unlimited number of attendees

- Laptop and Desktop PCs

- Standalone and server installations

- Individual or batch submission

- Desktop and lapel microphones

  Here's an interesting feature:
"The Acappella playback assistant floats above your chosen word processing application and can be positioned anywhere on the screen as well as minimised for convenience."

  Very, very cool stuff.
  We hope to hear more from this obviously very advanced firm.

AT&T Navigator gets ho-hum user responses..

2008-04-09T14:19:00.000-07:00

AT&T launced it's "Navigator" service at Wireless CITA 2008 and it's off to a rocky start. The new service features interactive speech recognition which seems to work well, but the GPS and routing configurations are getting some complaints already in popular user forums..

It's a built-in feature for these AT&T handset models:

BlackJack™ by Samsung
BlackJack™ II by Samsung (Real-Time Traffic compatible)
HP iPAQ hw6510/6515
HP iPAQ hw 6920/hw6925
Palm® Treo™ 680
Palm® Treo™ 750
HTC Tilt 8925 (Real-Time Traffic compatible)
AT&T 8125
Nokia E62
BlackBerry® 8700c (Real-Time Traffic compatible)
BlackBerry® Pearl™ (Real-Time Traffic compatible)
BlackBerry® 8800 (Real-Time Traffic compatible)
BlackBerry® Curve™ 8300 (Real-Time Traffic compatible)
BlackBerry® Curve™ 8310 (Real-Time Traffic compatible)
Motorola L6
Motorola L7
Motorola v3i
Motorola v365
Motorola v557
Motorola MOTO Q™ 9h Global (Real-Time Traffic compatible)
Nokia 6682
Pantech Duo™
Sony Ericsson W300i
Sony Ericsson w600i
Sony Ericsson W810i
Sony Ericsson Z520a
Sony Ericsson Z525a

and is available through AT&T to these devices, as an account add-on:

Palm® Treo™ 650
AT&T 2125
HTC 3125
AT&T 8525

and/or other "AT&T Navigator approved mobile devices".

Navigator also offers updated estimated arrival time(s) and traffic information.. but those services also appear to have a few inherent bugs, too.

Another valid & common complaint we're seeing:
The product is obviously TeleNav, but Telenav refuses to support it and calls to AT&T offer no individual dept. for support, nor does AT&T Customer Service seem to be aware there is such a product, or where to direct calls.

Jott enables dictated email replies, on Blackberry

2008-04-09T02:44:00.000-07:00

Jott (we've blogged about them before) has rolled out speech recognition to several Blackberry models, the 8800, 8300 and 8100 - that allows users to reply to emails by speech alone. It's a free beta download for now, and offers options for “Reply with Jott” and “Reply All with Jott.”

Jott also supplies users with a copy of the transcribed email, which can be pretty helpful in tweaking recognition accuracy and spotting/preventing (inevitable) transcription nuances.

The Jott web page can be viewed here.

Fluency Voice gets transcription accuracy patent

2008-04-08T18:46:00.000-07:00

Fluency Voice Technology announced on March 7th that they have been granted an interesting patent on tweaking recognizer accuracy.

The patent revolves around sending speech to the recognizer multiple times, and each time distorted a bit differently. All the resulting recognitions are then compared; an evaluation is done to decide which result(s) is most likely to be correct - that one is returned to the application. Fluency says they have applied this technique to all leading speech recognizers.

Via the press release:
"Dr Trevor Thomas, the inventor and Chief Scientist at Fluency, stated 'This invention will deliver important improvements to recognition accuracy and will increase the performance of our spoken dialogue systems when compared to similar dialogue systems that just make conventional use of a speech recognizer'.

Interesting stuff. We're waiting on feedback from some of our trusted sources to see just how far-reaching they think this technology is, re: transcription accuracy of continuous speech!

Sony announces enhanced Handheld Recorders

2008-04-08T08:51:00.000-07:00

Sony-Europe’s IT Peripherals division has announced seven new handheld recorders that declare its desires to dominate the digital dictation marketplace.

They each incorporate high audio fidelity, increased recording times, memory capacity and impressive playback features at nicely competitive price points to capture student, business and professional consumers.

The 'Professional' model numbers are the ICDSX68, ICDSX78 and ICDSX78DR9; the 'Business' model number is ICDUX60B and the 'Student' model numbers are ICDB600, ICDP620, ICDP630F.

Via the Sony-Europe press release page:
"The market for digital dictation machines is still very important, particularly with voice recognition software making transcription easier”, said Mikuni Shikada, product manager, Sony Europe's IT Peripherals division.

Satoru Iehira - A study of Vista's Speech recognition

2008-04-08T07:06:00.000-07:00

Satoru Iehira works at the Japan Center for Persons with Disabilities, and he doesn't use his keyboard. At age 15, Satoru Iehira received severe cervical spinal cord injuries.

"The operating system is easier to use. Speech recognition makes it so much more efficient than just using the keyboard," says Satoru, in reference to the Windows Vista™ Speech Recognition system. Using his wireless headset, Satoru performs all his work tasks everyday in Vista absent any keyboarding at all.

Via the Microsoft.com original article:
"Satoru especially likes the new mouse grid feature of Windows Speech Recognition in Windows Vista. With mouse grid, the computer screen is divided into a grid of nine, with each area numbered sequentially. The user selects an area by voicing the number, which then moves the cursor. The selected area is then further divided into a grid of nine, and the selection process is repeated in order to pinpoint the desired icon or button."

The complete article at Microsoft.com can be read here.
Its very cool to see real-world examples of Vista's speech recognition
working so well for the disabled...

SendChat - new universal speech-to-text messaging!

2008-04-07T10:32:00.000-07:00

TMCnet reports today that SR Virtual has developed SendChat, a "state-of-the-art, voice-to-text SMS" that mobile users can download to any mobile phone, regardless of which wireless carrier they are using. SR Virtual notes that SendChat will install as easily as a new ringtone, (welcome news to those of us who don't fancy tiresome fiddling with mobile phones..)

TMC further reports that SendChat uses smart technology that continues to learn the user’s vernacular and diction; thereby increasing its transcription accuracy with every use.
Very Cool.

SendChat is server-based which is why it will work with phones on any wireless network, and also spares users the tedious chore of updating new versions as well.

We don't have a download address, yet, but we will contact them shortly and see if we can glean further info; this promises to be a godsend to those of us who do text, but hate the "thumb typing" that goes along with it!

BlueAnt's new speech recognition gadgets - cool!

2008-04-04T12:47:00.000-07:00

Via PCMag.com, today - At this year's CTIA Wireless conference:

"BlueAnt showed off three new Bluetooth-enabled products—two of which offer voice recognition—that the company had originally announced back in January at CES 2008. Its V1 Voice Controlled Headset features Sensory, Inc.'s BlueGenie Voice Interface, which eliminates having to memorize complicated sequences of button pushes. Instead, you talk to the device and (in theory) it tries to figure out what you want it to do. The V1 also includes dual microphones along with Voice Isolation Technology for more effective noise cancellation, wind noise reduction, and better sound quality.

The second model, the BlueAnt Supertooth 3, is an upgrade to last year's Supertooth Light hands-free device. Like the older model, it either clips to your car's sun visor or sits on your desk. It builds on the former model's text-to-speech technology, which announces incoming callers names and caller ID information. The Supertooth 3 lets you activate voice dialing, answer calls, reject calls, and redial all with just the sound of your voice, and also includes a DSP chip for noise cancellation."

Comparing SpeechMagic to Dragon (sort of)

2008-04-03T09:13:00.000-07:00

The SpeechRecognition blog, an excellent site that focuses on speech recognition in the Healthcare Industry has posted a comparison of sorts between Philips SpeechMagic (a network solution) and Dragon NaturallySpeaking (a desktop solution).

A sysnopsis of its author, Claire Betis' conclusions:

"Both products offer a similar choice of medical dictionaries, covering general medicine and a number of specialties, in a wide range of languages."

"SpeechMagic was designed as a network solution while Dragon was originally made for individual users in the consumer world... I am even tempted to conclude this SpeechMagic-Dragon comparison thread by saying both products shouldn’t be compared in the first place."

We agree with No. 2, wholeheartedly. SpeechMagic is sold through various industry-specific vendors, and the support structure is accordantly different; it is network based and not really comparable to a desktop speech recognition program that doesn't offer (nor claims to) any file management and workflow features and/or any server-side implementation whatsoever, for that matter..

** Additionally, two of our members have dealt with Philips directly regarding a project for Windows Vista™ speech recognition, and we have to say that Philips' responsiveness re: support and communication really put Nuance to shame, IOHO.

Rob's Rhapsody Alert - 2 New Programming Videos

2008-04-03T08:14:00.000-07:00

Rob Chambers (Speech Program Manager for Microsoft) has posted a notice in his Rob's Rhapsody blog about two new videos in MSDN.
They are:

"How Do I: Get Started with Speech Recognition?
Will Depalo, Microsoft MVP, "explains the runtime and development requirements for doing speech development natively with Visual C++.
In addition he discusses create grammar files and how to compile them."

"How Do I: Use Speech Recognition in an Application?
Will explains how to use speech recognition in the applications that you build with Visual C++ so that your users can control them with their voice.
In addition, he explains how to set up the development environment and how to use the Platform SDK's grammar compiler."

The MSDN pages offer video and audio downloads in all formats as well as embedded Silverlight videos.

Speech recognition gets increased public confidence

2008-04-02T18:26:00.000-07:00

Callcentres.net has released a study in Australia with some quite welcome revelations..
The high points --

Overall, customers were significantly more satisfied with their speech recognition experience in 2007 than they were in 2005.

The research also shows that speech recognition is the preferred self-service interface; 66 percent of survey respondents preferred speech across the internet, & 59 percent preferred speech recognition over touch-tone (DTMF-driven) IVRs, when using the telephone.

Dr. Catriona Wallace, a director of callcentres.net said: "Confidence has emerged as a key factor influencing satisfaction with speech recognition. The research showed that frequent users of speech technology have a statistically significantly higher level of satisfaction with the experience than new or inexperienced users.

"It's also interesting to note that while men are more willing to try speech recognition, it's women who are more likely to become real advocates of the experience once they've used it," Dr. Wallace explained.

Speech-enabled Yahoo oneSearch is released

2008-04-02T14:25:00.000-07:00

Today at CITA Wireless 2008, Yahoo announced version 2.0 of its oneSearch mobile search application now includng Voice-Enabled Search.

A combination of predictive query entry and speech-recognition provided by vlingo, oneSearch is only available now for select Blackberry devices including the 8800 series, Curve, and Pearl, but Yahoo stressed that other handset support would follow shortly.

"Consumers can search for anything, including flight numbers, locations, Web site names, local restaurants, and more, by simply speaking," a release from Yahoo detailed. The voice-activation software is now available for download on a number of RIM's BlackBerry devices, and Yahoo has said that over the next few months it will be compatible with more handsets.

We're thrilled to see speech recognition emerging as a driving force for mobile search. We'd hope that Yahoo! and many others will begin to use vlingo's (the only close 2nd to Microsoft's voice searching on Windows Mobile/Smartphones) technology to expand and tweak mobile-centric searches.

Even though hurdles still exist for mobile-centric speech searching (noise canceling, poor voice signal quality) it’s begun to receive some serious integration as of late. Other outfits like Free411, Goog411 and Ask.com are using speech recognition technology; and the new ChaCha has a pretty robust speech recognition built into its new mobile-centric searching.

Microphone in your tooth? Available now!

2008-04-02T10:04:00.000-07:00

A company called Chinavasion is now in production of, yes, you read it right - a Bluetooth microphone inside your tooth of choice.

Per Chinavasion's web page:
"The durable composite resin filling is designed to fit in a hole 2.2mm in diameter and 1.7 mm deep and will pick up sound and vibrations from your mouth to produce incredibly clear sound.. never forget your trusty bluetooth kit ever again, simply install and forget".

It's a unique concept, that's for sure. This mandible-to-microphone technology's been around a while, and works very, very well.
(E.G. Aliph's Jawbone headset).

Are we seeing the future of microphones .. ?

Nuance challenges SpinVox in voicemail-to-text

2008-04-01T19:16:00.000-07:00

Nuance Communications, Inc., announced today at CTIA Wireless 2008 the "Nuance Voicemail to Text". Offered via wireless carriers, transcribed messages are sent to users as SMS or email messages.

Move over, SpinVox, a big dog is headed for your porch..

“Converting voicemail to text is a powerful and simple concept. But implementing a highly scalable semi-automated service is far more complex and requires highly accurate speech recognition – technology that takes decades to develop,” said Steve Chambers, president, mobile and consumer services division, Nuance. “The Nuance Voicemail to Text Service integrates speech technology with over 3,000 Nuance transcriptionists, hosted in a Nuance-owned facility, with proven security, scalability, and reliability.”

Looks like SpinVox is about to get a real run for the money!

Catalog ordering, with mobile speech recognition!

2008-04-01T18:42:00.000-07:00

France Loisirs, the French version of a mini-Amazon.com, has now selected Atos Worldline to host and operate a new automated telephone order service, based on speech recognition. The service is named “Commande Flash” & both smooths out / combines the different purchasing channels already available and reduces human-handled calls.

Thanks to speech recognition technology powered by Nuance, the caller speaks key words, a membership number and the products they wish to order.

Marc Duteil, customer relations General Manager at France Loisirs noted “The members quickly adopted the ‘Commande Flash’ tool which provides real comfort, especially for mobile phone users."

Founded in the early 1970s, France Loisirs, a 100%-owned subsidiary of the Bertelsmann group (50% owner of Sony BMG Music Entertainment), now has 3.5 million members in France, one household out of five. With 24 million books sold per year, France Loisirs accounts for 8% of the French publishing market. The brand uses a multi-channel distribution network and has 208 shops in France.

Now, imagine a speech-powered ordering system for, say Amazon.com...

Navigating with speech, a la AT&T

2008-04-01T18:10:00.000-07:00

Via SlashPhone.com:
"AT&T announced today at CITA Wireless 2008, the immediate availability of its company-branded GPS-enabled navigation service, AT&T Navigator. The AT&T Navigator service features audible and visual turn-by-turn driving directions, including full-color moving maps, using GPS directly from your wireless phone. Working with TeleNav, the service is available on GPS-capable PDAs and handsets."

"The service also provides integrated speech recognition for address entry and points of interest search. You simply press a single button on your phone and speak the name of the business or address you want to find, and AT&T Navigator will provide voice and on-screen turn-by-turn directions to your destination. Integrated speech recognition is currently available on BlackBerry devices, but AT&T plans to make this feature, along with other value-added services, available on more handsets in 2008."

Cool. Very cool.

OnMobile / Nuance Solutions; The largest yet

2008-03-30T10:05:00.000-07:00

Nuance Communications, Inc, (NASDAQ: NUAN) today announced that OnMobile, a leading Indian telecom services provider, has now incorporated world's largest global deployment of Nuance Speech Solutions. OnMobile provides services to leading Indian telecom operators such as Airtel, Reliance Communications, Vodafone, Idea, BSNL and Tata Indicom.

India is noted as possibly the fastest growing telecom marketplace in the world with about 300 million people now owning mobile & wire line phones, and is growing by about eight million new users per month.(In the last financial year, India added more mobile-phone users per month than China).

Mobile phone users in India, for example, can even search for "cars" and "bikes" using their mobile by simply sending either word as SMS to 6677,and will get the latest listings of cars and bike in their cell phones. Users can also further refine search results, on make and city location.

OnMobile is continuing to expand in Australia, Malaysia, Indonesia, UAE and other countries in the Asia Pacific region by leveraging Nuance speech recognition solutions to support multiple regional languages, including Regional Accent English, Malay, Thai, Bhasa, Urdu, Malay. OnMobile's services now support 15 major Indian languages.

Nuance's Speech Solutions are well known in the auto industry. Nuance’s automotive speech solutions have been successfully implemented in more than 100 models from more than 25 automobile brands including DaimlerChrysler, Fiat, Ford, Nissan and Renault - totaling over 5 million vehicles worldwide.

Michael Thompson, VP and General Manager for Nuance's Mobile Search and Communication division says:
“Telecommunications carriers are increasingly looking to advanced speech solutions as a means of differentiating their services, driving new revenue, and improving customer loyalty.. OnMobile was one of the first companies to create voice portals with speech recognition.”

Speak, Speak.. Shoot and Kill !l

2008-03-25T14:29:00.000-07:00

Good news for both speech recognition and virtual gun enthusiasts: “Tom Clancy’s Rainbow Six Vegas 2″ will be released this week. The game, according to a Gamepro.com review, casts players as a “highly trained anti-terrorist specialist who roams around with his squadmates, picking off evildoers with an impressive array of firepower.”

Fonix provides the speech technology that fuels the game’s voice command system — one of a handful of companies involved in the gaming vertical market.

Datamonitor analyst Daniel Hong says speech recognition will continue its upswing in gaming, because a) Headsets are standard features for the Xbox 360 and Playstation 3, and b) Far more powerful recent CPU's that can handle the cpu-hoggish speech interfaces.
"User interface [UI] design is paramount in gaming," Hong says. "Speech recognition provides differentiation and opens up UI choices for the gamer."

Speech Recognition for iPhones?

2008-03-25T11:14:00.000-07:00

Mike McCue, of Microsoft's recently acquired TellMe voice recognition unit has noted to Fortune's Big Tech blog that his team is also excited about iPhone development "to tap into voice recording and location-based features".

Could it be that coolest phone around is about to get "wired for speech" by the maker of the best speech recognition in the world .. ?

I guess we'll just wait and see!

Samsung and Nuance renew and expand the deal

2008-03-25T09:54:00.000-07:00

Via The Journal of New England Technology:
Samsing and Nuance have renewed, and expanded their "local" speech recognition-via-cell phone deal; it's official. The deal is a renewal and expansion of a previous agreement between the two companies.

The new global licensing agreement includes Nuance’s full range of mobile applications, including VSuite, Vocalizer, and VoiceMode speech-based services and interfaces, which have been shipping in 160+ Samsung handsets for several years.

Nuance, owner of Dragon NaturallySpeaking, was founded in 1992 as Visioneer Inc. and has grown significantly in recent years.

In 2007, the company acquired seven companies, including VoiceSignal Technologies Inc. Nuance was named a finalist in the MHT/ACG 2007 Tech Dealmaker Awards. In its fiscal year ending in September of 2007, the company reported $602 million in revenue with a net loss of $14 million.

CNN endorses mobile speech recognition.. Finally!

2008-03-21T18:25:00.000-07:00

In a nifty article today on the international CNN website, titled "Tips and Tricks for your mobile device", CNN officially endorses speech recognition, and several cool applications (some we've blogged about) and states, for example:

"Give your thumbs a break

Need to send an e-mail or text message but your hands are tied? Voice recognition technology has made advancements that can take the burden off your text-weary thumbs."

Even better, via the article:
"Similarly, voice recognition software on your smart phone lets you speak into the phone and have that message show up on a computer it's synced with, says Sean Ryan, analyst for market research firm IDC".

For a news giant like CNN to publicly endorse speech recognition, (even though they use the infamous misnomer 'voice recognition') we're cheering..
And this to us is a very important milestone in the path to ubiquitous speech recognition .. !

Goog411's speech recognition goes hands-free

2008-03-19T18:06:00.000-07:00

Via eWeek - Google's superb local search service should become available over Bluetooth headsets, courtesy of a hookup between the search giant and speech recognition software maker Sensory, the companies said March 18.

Terms of the deal aren't public yet, but Sensory will use its BlueGenie Voice Interface software client to connect to Google's voice search servers, Sensory CEO Todd Mozer told eWEEK.

An excellent (exclusive) announcement can be read here..

Shopping by speech.. Cool!

2008-03-14T07:30:00.000-07:00

Keeping your grocery list up to date is now simple - press record, and speak to the SmartShopper! It then prints what it hears, with impressive accuracy.

This cool gizmo, (our HO) is yet another milestone in the advance of ubiquitous speech recognition...

The SmartShopper can recognize 2,500 of the most common foods and errands. And you can use the speech recognition feature to add unusual or exotic stuff, like squid ink and zatar, to the memory.

When it's not in use, the SmartShopper can be mounted magnetically on the refrigerator door or hung on a wall.

Bill Gates & speech recognition, once again!

2008-03-13T21:20:00.000-07:00

(Per the BostonHerald.com) In a speech to the Northern Virginia Technology Council, Gates speculated that some of the most important advances will come in the ways people interact with computers: speech-recognition technology, tablets that will recognize handwriting and touch-screen surfaces that will integrate a wide variety of information.

"I don’t see anything that will stop the rapid advance," Gates said, noting that technological change driven by academia and corporate researchers continued even after the Internet stock bubble burst in 2000.

Neither do we, and Bill has shown the global "Doubting Thomas" community just how effective speech recognition can be with Windows Vista™ ..
And if there's to be near-future advances, just imagine!

Recognizing -unspoken- speech!

2008-03-13T13:22:00.000-07:00

Imagine thinking something, and having it turn into continuous speech.. without saying it.

It's not science fiction, it's not "vaporware".. Ambient Corporation of Champaign, Illinois recently unveiled an incredible breakthrough - a device that recognizes and responds to words you don't speak.

The technology uses a neckband that picks up nerve signals directed to the user's vocal cords.
In the video below, Michael Callahan, co-founder of Ambient Corporation demonstrates the device, called the Audeo demonstrates the world's first "voiceless" phone call:

Even more incredible:
"I can still talk verbally at the same time," Callahan says. "We can differentiate between when you want to talk silently, and when you want to talk out loud." That could be useful in certain situations, he says, for example when making a private call while out in public.

The system demonstrated above can only recognize about 150 words and phrases - At the end of the year Ambient plans to release an improved version, able to recognize the individual phonemes that make up complete words and phrases - producing true continuous speech recognition.

Callahan also notes that the device doesn't have any risk of divulging inner thought; Callahan says producing signals for the Audeo to decipher requires "a level above thinking", users must think specifically about uttering specific speech for the Audeo to discern them.

Pardon the pun, but..
What will be thought up next?

The new Mobivox "Say it and Save it" Feature

2008-03-13T07:01:00.000-07:00

The calling service Mobivox that offers free international calling began offering a new feature title "Create a Contact" today.

This feature enables MOBIVOX users to add new contacts, This feature enables MOBIVOX users to add new contacts, by simply speaking a name to the service's recognition application, named "Voxgirl" !

Via the Mobivox website:
"Dial your local access number, and when VoxGirl answers, simply say 'Create a Contact', or press number 6 from a touchtone phone. You will then be asked to record the name of the contact you would like to add, and enter the telephone number using your telephone's keypad."

Cool!

Mobivox's Voxgirl incorporates advanced speech and noise profiling, trained noise model, "voice tag" and vocabulary size technology, and there is almost unlimited storage space for voice dial contacts.

Nitzan Shaer, the company's COO comments:
“This new feature will dramatically improve the speech recognition accuracy, and is especially useful for those with multi-cultural backgrounds and non-English contact names. These are precisely the people who use MOBIVOX the most to keep in touch with their home country and loved ones far away.”

MOBIVOX also uses artificial intelligence to identify a frequently dialed number that doesn't appear in the user's the contact list, and accoordingly then prompt the user to create a contact for that number; A handy feature for users that don’t have their address books readily accessible.

Also very cool.

That's not all Mobivox does that's impressive.. The service will sync your Skype contacts and make them available to call using the remote voice access system. You can also query the service to see which of your Skype buddies are online.

MOBIVOX also offers instant conferencing (allowing users to spontaneously add callers to an existing conversation), group calling, and the ability to transfer a call from one phone to another, as well.

Mobivox's business model primarily hinges on revenue from international calling; Users purchase chunks of up to $100 international mobile-to-landline credits at a time; and Skype users can call their Skype contacts without having to buy credit from Skype, either!

There aren't "extra" charges for Mobivox's service other than minutes you use up on your mobile (or domestic-calling) plan, and since Mobivox gives you a local number, you can avoid legacy long-distance per-call charges on landlines, where applicable.

An excellent piece on IVR downfalls..

2008-03-12T15:16:00.000-07:00

Brian Solomon, a TMCnet Web Editor has written a very nice article titled "Seven Major Obstacles to Successful IVR"

Brian covers these points:

No option to speak to a person

Poor or no hand-off to an agent

Poor menu prompt structure

Recording Messages

Voice Recognition Accuracy

Taking too long for frequent users

Insufficient testing

and does an excellent job of discussing them each in turn.
The article can be viewed here.

Encrypted voice recognition.. The new Biometric?

2008-03-11T20:15:00.000-07:00

Philips and PerSay have combined encryption software with technology that manages users' "voiceprints" and speech verification.

According to the Information and Privacy Commissioner of Ontario, voice biometrics technology has taken a big step forward in strengthening its privacy and security measures with the help of new encryption.

Voice Biometric Encryption, a process that securely binds a PIN or a cryptographic key to the speaker's voice recognition (not speech recognition) offers newer, better security.

Says Michiel van der Veen, general manager at Philips priv-ID Biometrics:
“If you start thinking about using sensitive biometric information in all kinds of applications, it means that your biometric identity is exposed in all kinds of commercial solutions and can suddenly become available to a whole lot of people.. The current solutions already respect privacy and adhere to strict guidelines. But when you add privacy solutions like we are offering today, then you basically make privacy inherent."

LumenVox's Speech Engine is `Avaya Compliant'

2008-03-11T19:30:00.000-07:00

The LumenVox Speech Engine, an automatic speech recognition technology designed for telephony applications with support for several languages announced Avaya Compliancy today.

Via the Avaya website page:
"LumenVox speech recognition technology enables the development and deployment of accurate and affordable speech-based solutions on Avaya platforms. On Linux or Windows, the speaker- independent Speech Engine powers speech solutions and platforms in Enterprise and SMB environments worldwide."

More than 1 million businesses worldwide, including more than 90 percent of the FORTUNE 500®, use Avaya solutions for IP Telephony, Unified Communications, Contact Centers and Communications-Enabled Business Processes.

Speech Recognition betters the HIT, says Philips

2008-03-11T14:53:00.000-07:00

According to Nick van Terheyden, Chief Medical Officer at Philips Speech Recognition Systems, the implementation of enterprise level Healthcare Information Technology (HIT) systems, such as EMR applications, promises to provide more cost-effective care in the future.

A quote from the CMO, at the 2008 The Healthcare Information and Management Systems Society (HIMSS) Conference.
“Speech recognition can reduce costs by 30 to 40 percent, and early users will have a very high competitive advantage.”
{HIMSS is the healthcare industry's membership organization focused on optimal useage of healthcare information technology}

Moreover, By bolstering speech recognition with Natural language Processing, then interfacing to language engines with mapping capabilities - "Not only are transcription costs reduced using speech recognition, but even more importantly next-generation speech recognition tools will allow clinicians to interact with medical standards even before a dictation is complete, says Mike Levy, Chief Medical Officer of Health Language Inc.

This is impressive - almost real-time, quasi-interactive speech recognition..

Says Mr. Levy: "For example during the patient encounter, the clinician could dictate into the SR system and be presented with pertinent information such as: decision support including drug information and drug interaction checking; clinical pathways to provide the latest evidence-based information about treating diseases; patient information such as handouts that can be given to the patient at the point of care; order sets such as recommended medications, tests, labs, and other orders pertinent to the patient; and suggested billing codes".

Says Mr. van Terheyden of Philips:
“Speech recognition and natural language understanding bridges the gap between clinicians and technology.”

Speech recognition for iPods?

2008-03-11T05:33:00.000-07:00

Patrick Lor has posted a small blurb in his Entrepreneur In Action blog about a speech recognition device that "that will automatically categorize your music library", to be made by Ivoxx Corporation.

This sounds extremely cool, and we've emailed Ivoxx to learn more..

Mobile browsing by speech.. it's time is coming?

2008-03-10T07:46:00.000-07:00

Austin Shoemaker, a former Apple Computer software engineer and now chief technology officer of Cooliris, makers of the new "picture-in-picture" link Preview software for Internet Explorer and PicLens, the full-screen 3D slideshow software has raised the use of voice again as the next paradigm for mobile device users.

Many of us can remember the Conversay speech-driven browser, circa the late 1990's, and now the terrific Windows Vista™ recognizer allows us to surf the Web easily - but both were/are PC based interfaces.

In a Slashdot article today, Mr. Shoemaker is quoted as saying:
"Voice, too, is finally beginning to play a significant role as an interface tool in a new generation of consumer-oriented wireless handsets. Many technologists now believe that hunting and pecking on the tiny keyboards of cellphones and P.D.A.'s will quickly give way to voice commands that will return map, text and other data displayed visually on small screens."

Mobile web surfing, by speech?
All we can say is... "Let's get started!"

Learning languages with speech recognition..

2008-03-06T03:54:00.000-08:00

The popular Rosetta Stone language learning system has improved "speech recognition" in an unusual fashion;

It improves your foreign speech learning by recording your voice and evaluating your pronunciation and accent, dynamically!

Over-the-phone note & task transcription

2008-03-05T06:04:00.000-08:00

Via Angel.com:
"SalesByFone from Angel.com makes it possible to access, update, and manage accounts, contacts and leads directly in salesforce.com through voice commands over the phone. With a simple phone call, you can record your impressions about a just-completed meeting, set a follow-up task, or connect directly to a contact".

Per PRWEB - March 5, 2008:
Angel.com, the leading provider of hosted, on-demand call center applications, has partnered with SimulScribe, the largest provider of voicemail-to-text services and visual voicemail applications, to integrate speech-to-text functionality with Angel.com products and services. The first offering using speech-to-text functionality is Angel.com's new Salesbyfone application.

SimulScribe's technology allows Salesbyfone users to transcribe meeting notes and other details over the phone and see notes appear, within seconds, in Salesforce.com contact records. Users can also automatically dial and send an e-mail to a contact simply by speaking it over the phone. These functions occur in near-real time, allowing users to quickly act on or respond to critical business situations as they happen.

Salesbyfone is the latest in Angel.com's suite of IVR (Interactive Voice Response) integration applications for Salesforce.com. Salesbyfone provides phone-based access to Salesforce.com accounts, empowering sales executives and other users to access, update, and manage key prospect information directly in Salesforce.com through voice commands.

"Speech Recognition" improves for deaf kids

2008-03-05T05:40:00.000-08:00

The March 2008 issue of Otolaryngology – Head and Neck Surgery demonstrates deaf children with Cochlear implants experience a 59% variance of in later reading skills, and the data was collected by assessing the early speech perception/recognition and production performance!

The speech perception and production skills at the vowel, consonant, phoneme, and word level of 72 children with prelingual, profound hearing loss were assessed after 48 mos of Cochlear implant use.

The children’s reading skills were subsequently assessed using word and passage comprehension measures after an average of 89.5 mos of CI use. The results indicated that early speech perception and production skills of children with profound hearing loss who received advanced Cochlear implants predicts the future reading achievement skills...

Original paper's abstract is available here.

PRWEB - Staggering speech recognition growth

2008-03-04T19:11:00.000-08:00

San Jose, California (PRWEB) -- Buoyed by the robust growth in developed regions, the global speech technology market , per http://www.strategyr.com/Speech_Technology_Market_Report.asp is portended to reach US$7.8 billion by 2010. North America and Europe collectively contribute over 91% of expenditures on speech technologies.

Automatic speech recognition markets, per http://www.strategyr.com/Speech_Technology_Market_Report.asp, represent the largest segment for growth.

Sales from automatic speech recognition products are expected to register about US$7.5 billion by 2010. Business portal self-service and call center applications are the biggest sectors for growth and sales in the speech recognition telephony software markets, constituting over three-fourths of all global shipments.

Major factors for automatic speech recognition technology's high growth include - the power and speed of the standard PC increased subsequently gaining the ability to process speech in real-time; and algorithms were enhanced to enable computers to distinguish correct patterns that inspire speech, without giving importance to speed of speech, accent or other parameters.

We say.. terrific .. !!

A speech recognition tablet PC, from Motion PC

2008-03-04T19:01:00.000-08:00

Motion Computing, maker of the impressive C5 medical tablet computer, has released a new rugged mobile tablet PC, the F5.

It includes very good speech recognition; You can also catch a quick chuckle at Engadget, where they compare the handle-held device to that other bit of hardware brilliance, the infamous Speak N’ Spell.

Speech-driven "Contact Portal" adds SIP technology

2008-03-04T18:37:00.000-08:00

Telephonetics VIP has improved it's time-tested ContactPortal, a speech-driven call routing system, with a variety of mainstream SIP-based PBX/ACD systems.

Via Comm Business:
"The enhancement has been added to address the growing IP market in which Yankee Group predicts a compound annual growth rate (CAGR) of 31.4 percent & Mike Matthews, Head of Product Management, a Telephonetics VIP, comments “We are committed to listen to our customers’ real needs and the addition of SIP support is just one example of our ongoing dedication to provide interfaces for our customers’ convergent solutions.”

SpeechWorks (Nuance) Exec. joins SpeechCycle

2008-03-04T14:30:00.000-08:00

Todd Barber, former VP of Telecommunication Sales at SpeechWorks (now Nuance) joined SpeechCycle, winners of the Speech Technology 2007 Market Winner award with their very advanced IVR Natural Language dialog that allows callers to articulate issues in their own words, and their IVR's "Continuous Learning" capabilities.

Speech-driven "Anywhere-anytime" data entry..

2008-03-03T06:46:00.000-08:00

A research team with the Canadian National Research Council's Institute for Information Technology (NRC-IIT) is working on a way to enter data using speech; they've created a multimodal field data entry (MFDE) application to help with data collection during concrete inspections. The researchers say that if workers are are using instruments or taking measurements they can use speech to enter data or information at the same time.

While background noise was somewhat of a problem the researchers have gone back to the drawing board to identify a better microphone for the application. Even with the noise issue respondents claimed they were able to complete tasks faster while at the same time being able to be more aware of their environment.

They've worked on actual mobile microphone improvements; Their research won "Best Paper" at the prestigious British Human-Computer Interaction conference, HCI 2007 about microphone performance in noisy ambience.

They are also seeking the best speech engine for noisy environments:
Per NRC IIT:
"We also plan to look at different speech recognition engines to see if we can improve the accuracy at higher noise levels."

Newest throat-mounted microphone ??

2008-03-01T08:26:00.000-08:00

Pro Idee, a UK website for the Denmark online retailer Pro-Idee GmbH & Co. KG is offering a pretty innovative microphone [click image for larger view in new window]:

Pro-Idee's specs. include the microphone offering nine hours of talk-time, 10db of noise suppression and complete Bluetooth feature functionality,
(Click here to read the CNET review).

~ We'd love to hear from anyone that's tried this hardware..

Dictate for MAC's are due Friday..

2008-02-11T03:32:00.000-08:00

MacSpeech's Dictate — the new native Mac speech recognition application that is built on Nuance's Dragon NaturallySpeaking, is slated to release February 15, 2008.
The demonstration video is rather impressive…

But it sure doesn't look like it will stand up yet, to the amazing Vista recognizer..

1 Hospital - 100% Speech Recognition

2008-02-10T14:48:00.000-08:00

The Hague’s Bronovo hospital in The Netherlands has converted to 100% speech recognition for all departments - it has improved service quality, and profits.

Says Dr. Pieter Lambregts, who oversaw the speech recognition for the Neurology group in the hospital.."The overall efficiency gain and time saving allowed us to increase our department’s activities by 20% without having to hire additional secretaries.”

Speech recognition is widely used in the Health Care industries in the Netherlands; SpeechMagic from Philips is the platform for over 80% of the speech recognition systems.

Wilfred Reinhard, Bronovo’s IT Manager noted “We wanted to realize the country’s first all-speech recognition hospital because we knew how critical the availability of clinical information is for the delivery of care.”.

The entire case study from G2 Speech is available here.

Goog411 speech recognition to GE phones

2008-02-08T09:30:00.000-08:00

The GE Premiere DECT 6.0 28821FJ3 has a cool new "GOOG-411" button centered on the handset, that get's instant free business information calls!

The button auto-dials Google’s free, voice-activated, speech recognition-driven business directory assistance service and becomes a feature on more than a dozen GE phones to be available in April 2008.

Connections are done for free, leaving your dial tone provider out of luck ;-) when it comes to directory assistance call revenues.

(This deal benefits Google in one particularly semi-interesting area, as it provides a "no brainer" option for even more users to give Google more phoneme samples it might not otherwise have gleaned, of independent spoken audio samples in it's quest for advanced speaker-independent speech recognition, as well)

Dynamic advertising via speech recognition in videos

2008-02-06T08:52:00.000-08:00

Cheap shots are often fired at Microsoft for being a little behind the "cutting edge" curve.

Not so, as we well know; And the world's leader in speech recognition technology has ventured into a huge leap forward yet again.. Dynamically served contextual advertising, via automated speech recognition, on the spoken audio in videos, from Microsoft's adCenter Labs' technology.

This technology enables ads to be rendered based on the contextual spoken audio in a video. For example, if the topic of the video was gardening, ads related to gardening or lawn improvement could be served in an adjacent text-based ad as the video played. For advertisers, this provides new & unique access to consumers.

The YouTube video below makes a "video worth a thousand words.."

..Wow....What else could we say?

Out Loud for Outlook - Source Code now available..

2008-02-05T11:50:00.000-08:00

"Out Loud for Outlook", developed by Nathan Carlson for Outlook 2007 using Visual Studio 2008 Tools for Microsoft Office, allows you to create a new Outlook rule that reads your designated email out loud when it triggers. You can also use speech recognition command & control, to open and navigate through your emails.

On the Code Gallery website, the source code is available as of February 1, 2008. Nathan's sample demonstrates:

Basics of developing an Outlook 2007 Add-in.

Consuming Outlook events.

Accessing e-mails.

Creating a Custom Action for Outlook rules.

Using Speech Synthesis.

Using Speech Recognition.

* If you are seeking full-fledged speech recognition integration with Outlook, we highly recommend Adondo's PAL.

Speech Recognition 2007, By Stephen Potter

2008-01-21T19:15:00.000-08:00

Stephen Potter has written a "What a Year for Microsoft Speech Recognition" blog post that's worth every word.

Congratulations on a great article and the year's resounding success!

A dead-simple speech recognition Response Point

2008-01-19T04:59:00.000-08:00

eWeek's Andrew Garcia has reviewed Microsoft's VoIP Response Point system, and writes that among other things, it contains "brain dead simple" speech recognition!

Via eWeek:"Additionally, the system can be used to answer certain common real language questions automatically. For instance, Response Point will tell incoming callers the office hours, whether they ask "What are your hours?" or "What time are you open?" or numerous other variations of that and a couple other questions."

Bill Gates noted at CES 2008 the next decade would mark the arrival of very natural user interfaces.. and we believe this is just one of many watermarks along the way.

Navigation, solely w/ remote speech recognition!

2008-01-09T09:25:00.000-08:00

NavStar Technologies, in partnership with Navteq, a provider of digital maps for vehicle navigation, has released "Voice Navigator" - an entirely speech recognition driven navigation device accessing only a remote server!

True, wireless remote speech recognition... via NavStar:
"No PC's, CD's, DVD's, tiny screens, difficult interfaces, or piles of 'stuff' to learn. Simply plug it in and start using it."

According to NavStar, there is even "planning intelligence" built in:
Users can plan their trip ahead of time, store it and then access the planned route with the push of a button.

The device interfaces with user's mobile devices, using their wireless broadband service. Navteq's "Points of Interest" database includes over six million listings including airports, restaurants, hotels, banks, gas stations and other popular destinations, or, subscribers can state the exact address desired.

Our techie hats are off to this wonderful advance in true wireless remote speech recognition!

I posted this... with Jott

2007-12-28T09:43:00.001-08:00

I am posting p this using the Jott application. I am doing this from my cellphone. If it happens to work incredibly accurate, it is because quite often, human transcribers are the ones typing what you are reading. (Click here to listen to the original audio) *Powered by Jott

We posted the above by cell phone, using the Jott application.

(We've blogged about cool stuff Jott does, before ;-). For a cell phone_to_web_application; Not bad, eh .. ??

Your "Talking Character" says Happy Holidays!

2007-12-24T12:59:00.000-08:00

Want to send a neat-o talking holidays card.. Truly a little different?

Check out PQ Computing's "Talking Photo" application - With a few clicks, here's what one can do, according to the Talking Character web page:

Use one picture to make realistic 3D faces for animation
Animate any human / animal photo, painting or drawing
* Automatically match lip movement with voice
Most major languages are supported!

'Ya gotta check this out..

A nice cool way to spice up the holidays, eh?

Distributed Speech Recognition is emerging..

2007-12-20T09:31:00.000-08:00

We posted an article about Distributed Speech Recognition ("DSR") a little over a year ago.

The great news is that among other big players in the speech recognition marketplace, SRI International, makers of the advanced Speaker Indepent DynaSpeak SDK, have incorporated Distributed Speech Recognition as an intregal part of the SDK.

From the DSR section of the DynaSpeak pages on SRI's website:
"To date, speech recognition systems have been deployed in two ways: on a remote server or pre-loaded on a mobile device. Either approach forced makers of mobile phones, PDAs, PCs, and consumer and automotive electronics products to accept tradeoffs. To eliminate design sacrifices, SRI has created a third mode of deploying speech recognition: DynaSpeak with Distributed Speech Recognition (DSR). With DSR, a user's speech is preprocessed on the user device and transmitted over a low bandwidth channel to a full-featured server-side system. The benefits are numerous: higher quality audio capture, lower cost per device, and centralized management of speech applications."

SRI isn't the only big player to incorporate DSR; Hewlett-Packard has been developing distributed speech recognition as a power-saving solution for wireless devices:
"We have shown that DSR can reduce the required systemwide energy consumption for a speech recognition task by over 95% compared to a software based client-side speech recognition system. These savings include the software optimizations of the DSR front-end as well as the savings from the decreased duty cycle of the wireless interface."

Nuance also built DSR into their OpenSpeech Recognizer 2.0 that's availaible with their Network Speech Solutions.

We cheer the efforts, and hopefully handset manufacturers will begin to support it inside 3G mobile phones; the "Chicken or the egg" dilemma David Pearce, DSR's chief developer spoke of at both speechTek 2005 and in his VoiceXMl articles is solved - now that it's "hatched" let's hope it continues to grow!

Here you can find products, thoughts, ideas and projects that use hands free and mobile devices to make speech recognition a useful and rewarding tool...

Mobile speech recognition advances!

2007-12-17T10:29:00.000-08:00

AT&T Wireless announced today it has partnered with Barcelona, Spain based Code Factory to bring very advanced speech recognition services and highly advanced screen reader capability to AT&T Wireless phones.

Code Factory's "Mobile Speak" is available for mobile phones using Symbian Operating System versions 6, 7, 8.x and 9.x running the Series 60 Edition interface; nearly all Windows Mobile Smartphones and Pocket PC's.

Mobile Speak for Symbian-based mobile phones includes impressive controls for the Code Factory mobile screen readers such as:

"Commands that allow changing of important settings on the fly, such as keyboard echo, punctuation level, verbosity level, speech rate and volume."
"Commands for repeating or spelling the last spoken text, reading the whole screen or just parts of it like the softkeys, as well as interrupting speech output or toggling speech mute."
"Command Help Mode available anywhere on the phone."

But these are only the true speech recognition commands; the overall speech interface for Mobile Speak itself offers a truly amazing set of features. The Mobile Speak for Windows Mobile Smartphones and Pocket PC's includes Microsoft Voice Command for wireless control of the device, whether or not a native recognizer is already present in the device.

Additionally, the Mobile Tools product suite (which includes Mobile Speak) includes Remote Access applications that allow the users to remotely perform tasks on their mobile phones, even if a screen reader or screen magnifier is not yet installed.

Code Factory boasts a rather admirable mission philosophy..

"Some Mobile Tools are developed by Code Factory to meet specific needs of Mobile Speak and Mobile Magnifier users. Other Mobile Tools are applications from 3rd-party developers and then supported by Code Factory to work with our screen readers and screen magnifiers. Our goal is not limited to just making mainstream mobile technology accessible, but also to harness its full potential and offer users a multipurpose solution in one portable device."

Speech recognition & AI, formatting your to-do lists?

2007-12-14T05:57:00.000-08:00

Meet CALO - An artificial intelligence project Funded by the Defense Advanced Research Projects Agency (DARPA), and coordinated by SRI International. What's interesting to us is it's research into using speech recognition to understand, organize and assemble task information.. from everyday meetings.

CALO promises, among other things, to use speech recognition to make a transcription of what's said during meetings, and using it's understanding of a user's projects/contacts, to compile to-do lists and appointments!

Imagine.. When you logon every morning, your computer reminds you it's assembled a list of tasks and meeting requests from yesterday's meeting - while you were asleep. How cool is this?

The military's research into AI coupled with speech recognition goes back at least a quarter of a century, in 1982 a study was published regarding different AI alogorithms applied to speech recognizers.

The study of artificial intellience is thought by many to have originated in 1947 with the mathmetician Alan Turing, although it seems he initially believed 'Machine Intelligence’ to be an apparent contradiction in terms.

What CALO promises is a far cry from Turing's "Can a machine be intelligent?" musings; and we believe it's yet another step towards fulfilling Bill Gate's recent prediction, that speech recognition will quickly become the next user paradigm!

Speech recognition's accuracy better than human transcription..

2007-12-13T04:18:00.000-08:00

Welcome news for speech recognition proponents!

HealthImaging.com (a site for Healthcare IT professionals) posted a news article yesterday, December 13, about a presentation at the Radiological Society of North America (RSNA)'s annual meeting last month, documenting that the reports which were manually transcribed by humans, showed higher error rates than the reports that were transcribed through speech recognition!

John Floyd, MD a partner in the 24-member Radiology Consultants of Iowa (RCI), reported “The rate for significant errors, requiring the preparation of an addendum, was 0.6 percent for speech recognition and 2 percent for traditional transcription.”

Floyd also noted speech recognition significantly increased his firm's efficiency: "Separate data for this practice indicated that average turn-around time for traditional transcription was greater than 24 hours while that for speech recognition was less than one hour.."

Dr. Floyd further confirmed that the accuracy rate for speech recognition reported by his group was independently verified by 3rd party analysis, conducted at one of the hospitals his partnership services.

In an On10Net blog post, Bill Crounse MD, Healthcare Industry Director for Microsoft Corporation predicted earlier this year that speech recognition would open up new vistas in the healthcare industry..

We're pleased to see his predictions coming true!

MIT's Browsing through speech inside videos

2007-12-12T06:57:00.000-08:00

MIT's new CSAIL (Computer Science and Artificial Intelligence Laboratory) "Lecture Browser" may be raising the bar on searching the spoken audio in videos, for indexing. In fact, it's receiving over 20,000 hits per day - and it is to date only indexing lectures.

Originally funded by Microsoft and first announced in August, the Lecture Browser offers results in either video or audio timeline sections, the section containing the search term is highlighted, and snippets of surrounding text are displayed. The searcher can also "jump" to the relevant section of the video directly from the index, as well.

There are some impressive features built into this rather advanced application.

Optimized Speech Transcription:
- The speech recognition has been trained and configured to accurately transcribe accented speech, using short snippets of recorded speech spoken under various accents.
Accurate recognition of uncommon words
- A massive vocabulary has been trained into the system's lexicon, allowing it to recognize extremely uncommon scientific terms, et al

The system includes software designed by MIT, that segregates long strings of sentences with common topics into high-level concepts.
- "Topical transitions are very subtle," says Regina Barzilay, professor of Computer Science at MIT. "Lectures aren't like normal text."
  The software takes (approx) 100-word blocks of text and compares them to calculate the number of overlapping words shared between the text blocks. High repetitions of key terms are given more weight, and chunks with the highest rate of similar words are grouped together.

MIT's efforts to optimize the user experience are on-going. In the future, users will have the ability to contribute transcript corrections much like the "Wikipedia process", further improving transcription accuracy.

Even more impressive: MIT's plans include the ability for the system to learn from these corrections, as they propogate to other transcribed lectures.

A more comprehensive overview can also be read here.

Twitter by speech!

2007-12-08T18:52:00.000-08:00

The short_&_sweet?

Using www.jott.com; Sign up for a free Jott account and then connect the service to your Twitter account. Then you can call a Jott phone number, tell the system where you want your comments to go, and then you leave a voice message that gets converted to text and posted to your Twitter.

From the OpenSourceMarketer Post:

"The service is extremely accurate and easy to use and since twitter can be connected up in lots of places you could effectively generate new content in hundreds of places just by making one phone call and essentially leaving a voice message.

The Jott service also offers the ability to connect to Tumblr, WordPress, Yahoo Groups, LiveJournal, Amazon, and lots of other sites which is great because it puts blogging and written social communications in your pocket."

How cool is that?
True, wireless and remote speech recognition. And no gadgets to buy.

And just the other day, one of our members posted an article in Techdirt about this being the killer mobile speech recognition application!

Speech-controlling Bluetooth devices..

2007-12-08T09:37:00.000-08:00

Foxlink Group and Sensory, Inc. have teamed up to bring speech I/O (speech recognition and spoken prompts) to Bluetooth products.
How cool!

Foxlink's US Operations President, Mr. James Lee, notes: “Our customers want improved user experiences for their headset products. With Sensory’s voice recognition and speech output technologies we can add more features, while making the products easier to use".

According to their announcement's web page, speech recognition makes Bluetooth device controls far more convenient and intuitive; and having a pleasant voice confirming status and commands, rather than beeps or light flashes, adds to the VUI experience.

Once again, speech recognition easily solves a common problem: "Do I hold down the right button, or the left button? Where did I store that manual, anyway .. ??"

Moreover, analysts are predicting speech control over devices, commonly referred to as VUI (Voice User Interface), will quickly become a common device interface.

"I think this is an intermediary step for what’s going to come.." says Datamonitor analyst Daniel Hong.

Foxlink is one of the world’s largest independent manufacturers of Bluetooth headsets, a manufacturer and/or ODM for most of the major brands that use 3rd party silent OEM's.

Sensory is a market leader in embedded speech technologies and the 1st speech technology provider to port a VUI to a single chip Bluetooth solution with Cambridge Silicon Radio, a premier Bluetooth chipset manufcturer.

Searching the audio in videos, with speech recognition..

2007-12-08T02:51:00.000-08:00

In an interview with Everyzing's CEO Tom Wilde, he discusses a valuable step forward in letting Web users find the videos that they are interested in - using speech recognition to parse and publish the spoken audio streams, of videos that are posted to the Web.

This powerful, useful implementation opens up "discoverability of multimedia within a Web search" says Wilde, and he's very correct. No longer does a searcher only find results centered on the just the metadata of a video, but the actual audio content of that video, as well.

Everyzing's 2-part speech recogntion technology first turns the audio of videos into text; then it analyzes, extracts and indexes key terms, entities and concepts within the text. This enables new multimedia category indexes containing search related terms that may only appear briefly or just by mention inside any video's spoken audio!

The recognition, analyzation & indexing process's core is from BBN Technology. Everyzing is combining it's Byblos engine, and BBN's two Information extraction from Speech and Information extraction from text technologies. BBN is a leader in speaker-independent recognition accuracy for speech in different environments, including telephony and broadcast news.

CEO Tom Wilde has been frank about the present shortcomings; He notes the accuracy drops (understandably) against background music and/or multiple speakers. But for the infotainment & news markets he's targeting right now, the technology should offer a significant improvement over what's currently available, he says. "I think we'll look back in a couple of years and say, 'Of course the content of multimedia files needs to be searchable,'" says Wilde. We agree!

A comprehensive look at the core technology by Technology Review can be found here, as well.

Thousands of voices, incredible recognition!

2007-12-04T21:13:00.000-08:00

In an article published online August 11, 2007, IBM Research announces the development of a new Cell Broadband Engine™ ("Cell/B.E.") processor. This new Cell/B.E. is a streaming multiprocessor who's architecture contains a general-purpose IBM PowerPC processor, working with additional special-purpose processing cores jointly designed by Sony, Toshiba, and IBM.

This processor represents a very significant leap forward; for both speech recognition "in general" but primarily for what we all love to hate - the infamous IVR's we hear answering most of our phone calls today, to most companies.

IBM notes: "Speech recognition systems in telephony applications for automated call centers represent the largest segment of the speech processing market". How true, and how sad the IVR performances that we often encounter really are. Who hasn't begun to pound on the "0" key and/or shout "Operator! Customer Service!" in desparation when encountering one of these infamous sad perfomers..

Current multi-channel speech recognition systems, that use "clusters" of traditional CPU's can manage between 20 to 30 speech channels in real time.

The Cell/B.E. can handle thousands of simultaneous voice channels in real time, and IBM states "On both the Cell/B.E. processor and the software platforms, recognition accuracy was 99%".

Take a look at the tremendous difference in performance, below:

(In the Table above, 1 RTC = 1 second of audio per 1 second of processing time)

The performance measurement above is based on speaker-independent recognition of a small vocabulary, based on the TIDIGITS corpus that included the digits "zero" through "nine" including the "oh" pronunciation for zero, using a propreitary IBM speech recognition engine (who's recognition algorithims are explained in detail). It's obviously fairly simple recognition testing, even though it included speakers of different gender and dialects.

Nonetheless, IBM notes the "performance of our prototype speech recognition engine on the Cell/B.E. processor can be extended to production systems because the SPE kernel programs were designed to scale with model and language complexity."

They further point out that due to the raw computaional power and memory management of the Cell/B.E, when used with systems that have large vocabularies and complex grammars, there will still be much higher recognition accuracy even when complex recognitions are put to task.

Additionally, they plan to add in models built on the Texas Instruments/Massachusetts Institute of Technology ("TIMIT ") model which is designed specifically for automated speech recognition systems.

Also interesting is IBM's plans to optimize the Cell/B.E. for recognition of compressed speech signals, and, they mention pursuing the proverbial Holy Grail, software-based noise canceling: "...we are trying to classify speech from background" !!

The research team goes on to say in their conclusion:
"We have implemented and demonstrated a prototype speech recognition engine that is capable of processing approximately 1,000 speech channels on a single Cell/B.E. processor. The kernel computations are designed to be highly scalable, and we expect this performance result to generalize well to commercial speech systems".

What a terrific development. IBM's embedded ViaVoice won Speech Technology Magazine's 2007 Market Leader award; and some of us remember when ViaVoice for continuous speech recognition (circa 1997, 1998) was the the best of the best. We admit we are definitely looking forward to seeing this technology emerge into the mainstream, and push speech recognition to new limits!

Wireless, remote speech recognition driven spybots!

2007-12-04T04:53:00.000-08:00

Robert at RoboDance, has created a video of some incredible wireless, remote speech recognition functions he's added into a WowWee Roboquad Robot. It is quite easily used as a "Spybot" for remote surveillance; and can be controlled remotely, across the Internet using speech recognition from anywhere! It's called RoboDance 4.

Using Skype's video call service, and an infrared link from the host PC to the robot, Robert shows how he makes this robot do some amazing things..

We could tell you more, but the video below has to be seen to be believed.
(** What's particularly impressive is during the video, Rob's robot listens only to it's commands, even though they're mixed with his video's continuous speech narrative!)

The details of the necessary hardware & software are available Here,
and Robert says the Robodance 4 is available now; joining his mailing list here gets notifications of how to purchase this pretty darn cool robot!

.

A speech-enabled newsreader, for the MAC!

2007-12-02T15:42:00.000-08:00

A news reader that supports speech recognition for the MAC is now available..
It's called MT-NewsWatcher.

It can be downloaded, from here

.

Excellent comments from a reader; & an answer..

2007-12-01T20:14:00.000-08:00

One of our readers has posted some very germane comments.

The first segment says:
"I don't know about all the areas your are talking about, but I do know that at least in my little corner of the world, the medical community either records notes and has those notes transcripted by a human using one of those little pedals, or if they are using speech recognition, have mandatory human review for inaccurate translations."

We're Microsoft fans, of course; but as of yet, Microsoft hasn't published any vocabularies. However, Nuance has released Dragon NaturallySpeaking Medical 9, with 14 medical specialty vocabularies covering 60 subspecialties which is receiving glowing testimonials in speech recognition newsgroups. Nuance says that with training, accuracy at 99% is achievable, and there's good evidence to support that claim.

As to whether or not physicians should investigate if speech recognition can now be trusted, here is a very, very interesting article from the Speech recognition blog, that specializes in covering speech recognition in the Healthcare industries. The short answer: Yes; and an overwhelming "Yes" !

Many users of speech recognition don't know and aren't told that accuracy is very closely related to the input mechanism (hopefully a wireless headset!) that's used to give the recognizer speech data. It is mission-critical, actually.

All the training in the world can't overcome an inherently bad voice signal. Remember the age old euphamism, "Garbage In, Garbage Out"..?
That holds especially true, for speech recognition. In the old days, we can remember when speech recognition software shipped complete with a $4.00 (retail) headset - and the software makers just couldn't figure out why their sales stayed minimal.

{** If anyone reading our blog wishes to find a pre-tested, pre-qualified headset or other microphone type for the best possible input performance, please consider contacting eMicrophones.com - the best and most trusted web vendor for speech recognition quality hardware.}

Our reader's comment's 2nd segment reads:
"And while the technology may be advancing quickly, for the common person, they don't seem to use it for much, and if they do use it, say on a cell phone or call center, it's hardly flowing speech recognition and is often a pain or at best, more timely.

How right you are!
An excellent piece about what really goes on with "voice over cell phone" can be found here in a post by a_chameleon, one of the Team members.

As to call center IVR performance, before we comment to that we've sent emails to Terry Gold and Marshall Harrison who are without doubt the leading experts on Microsoft Speech Servers and related IVR matters.

Our reader's 3rd comment segment reads:
"Maybe the reason it's considered as a flop by some is because the hollywood aspect of speech recognition. We expect it to do the things we see in star trek. Those are unrealistic expectations, of course, but they do exist. And the speech recognition industry doesn't necessarily abstain from playing on that hype when seeking funding, seed capital, advertising revenue, etc..... :)

Our best answer to that is - Everyone who uses desktop speech recognition should waste no time migrating, to the awesome speech recognition built into Microsoft Windows Vista™. Once anyone's watched Rob Chambers interview with Dr. Crounse video.. there shouldn't be any question - the "Star Trek" and "Hollywood" quality speech recognition we've anticipated for years.. is definitely here now!

Check back tomorrow for more!

Speech recognition - a "Top 10 Flop" says CNET Blogger

2007-12-01T03:16:00.000-08:00

Someone's forgotten to tell Steve Tobak, over at CNET, about where speech recognition really has evolved to these days.
He's declared speech recognition one of the "Top 10 Technology Flops"...

Hmm...
Let us count the ways?

Beginning with the medical profession - 40,000 active physician users generating about 18 million lines per month with speech recognition technology, in the US alone.

Or Field Automation... Equipment inspectors, mechanics, insurance claims adjusters, real estate agents, couriers and other highly mobile, hands-on employees are now using embedded speech recognition on portable devices making data entry and lookup faster and cheaper.

Smart Phone users easily searching the web by voice alone, with uncannily accurate and powerful results.

Notwithstanding smart phone capability - over 60% of "ordinary" cell phone users can just say to their cell phones: "Call steve tobak" and that phone number will ring!

Then there's Ford, (the car manufacturer); Do the words "Ford Sync" ring a bell? As in "play artist so-&-so" or "Call the office".. look ma, no hands!
And on the subject of cars - there is VoiceBox's new embedded speech-controlled technology that now allows us to control what our car's various features do and when, control our car's radios and navigation systems.

Is it also curious that GM is busily seeking Telematics engineers that can "Provide technical leadership for advanced speech technology development"..??

Let's not forget the major news networks over recent weeks, where one cannot watch in the AM without seeing at least one advertisement for Dragon Naturally Speaking?

As to "keyboarding" - Would this video help bring us up to speed, a little?
Where Rob Chambers does just about whatever he wants with Windows Vista™ built-in speech recognition?

Moving right along to the US Military and a company called Adacel, building technology allowing military pilots to interact with modern avionics, using simple voice commands, built on the awesome Microsoft ESP platform?
Or the IBM MASTOR speech-to-speech translation systems presently used by the military, in Iraq?
Speaking of IBM, does their joint venture with Cisco Systems to build speech driven self-service kiosks inside banks tell us anything?

And then there is the globally popular SpeechMagic system from Royal Philips Electronics.. which now offers extremely accurate remote speech recognition across a network, in 23 different languages?

But at the end of the day, we ask:
You've called a large company, sometime lately? What exactly do you think you might be doing when you talk back to that computer voice.. pray tell?

We hope our readers will forgive our quasi-diatribe..
But speech recognition is one of the most pervasive technogies around us these days - and it's only getting better!

** We've been told by a very reliable, trustable source, since this post went public, that just because a blog may be viewed on the CNET site, doesn't just automatically mean that it was written by a CNET employee!

Low-level white noise, better transcription accuracy?

2007-11-28T16:53:00.000-08:00

Yes.. you read the title correctly!

In an article posted 11/27/2007, HealthImaging.com has noted a study at the University of Maryland Medical Center - "found that the introduction of white noise at certain levels as part of the acoustic background increased accuracy of speech recognition systems’ transcription capabilities", said Joseph Zwemmer, MD, who presented the results of the research.

This is actually pretty fascinating stuff. If white noise can be used to improve accuracy, then it's more than likely another step has been made, albeit maybe inadvertently, in the proverbial quest for the "Holy Grail" of speech recognition; to-wit software-based noise canceling.

The original article can be read here.

Hopefully, we'll be able to get some specific data soon from the University of Maryland as to what exactly comprised the white noise, what frequency ranges it included, details as to the sound itself, durations of specific frequency ranges, etc.

This has some very interesting possibilities..
Check back from time to time to see if the Medical Center has shared any data,
on just what type of sound the white noise was comprised of..

Cleaning the Loo and recognizing speech..

2007-11-25T06:35:00.000-08:00

Who would have imagined?

A group of deleopers for West Nippon Expressway Company Limited (NEXCO), one of the main operators of expressways in Japan has come up wht a "bug" that cleans the bathroom - and recognizes speech!

It's makers say it speaks politely, and is being designed for cleaning public restrooms at highway rest areas. It even comes with "access to current traffic information in case someone has the urge to spark up a conversation",,
How cool!

We posted an article about US market validation for speech recognition recently; it seems there's speech recognition enabled devices springing up across the globe, too.

Yes, it's a cliche musing but;
We wonder what's next..?
.

Google -and- Microsoft; Betting on speech-based searches!

2007-11-22T23:23:00.000-08:00

An article from MySpaceNews has another reference to..
"The development of increasingly precise speech recognition technology begs the question of whether Google and Microsoft will one day use it to "listen" to users, in order to serve them relevant advertising".

The article talks about how both Google, and the leader in speech recognition, Microsoft, are both building speech data banks.
Why?

Both internet giants are.. "using their free directory services to build vast, digital Petri dishes loaded with samples of users' speech patterns. Those patterns are in turn are being fed into the companies' myriad server computers, where they are analyzed in an effort to make their respective speech recognition technologies progressively smarter."

And again - why might that be, according to rumors?
"accurately understood search commands could be paired with equally relevant, and valuable, advertisements."

Nonetheless:
Rgardless of any presumed dark motives, the data these two highly evolved industry giants will quickly gather and analyze will undoubtedly become a giant leap forward in the holy grail of speech recognition to everyone - The proverbial Holy Grail of speech recognition for over a decade:
"Speaker independent speech recognition".

What a terrific development. It's more than possible a year from now all the wireless devices across the world will be interacting with websites in very new, very exciting ways!
.

Skype + Speech Recognition, powered by Google?

2007-11-22T12:47:00.000-08:00

Both Rich Tehrani at TMCNet and Jemima Kiss (PDA: The Digital Content Blog) have posted articles in the last few days about a circulating rumor..

Maybe Google's looking at a Skype acquisition?

This interests us because Rich has some cool conjecture(s)..

Rich wonders..

"You don’t think there are 100 propeller heads (said respectfully – I am a fellow propeller head) in the Googleplex working on speech recognition right this moment so if they acquire Skype they can immediately run contextual ads based on what you are talking about?"

and we've known Rich for over a decade... Rich isn't often wrong!

Of course, if this happens we hope this means to Skype users everywhwere (on wireless headsets, of course :-) that they'll be generating speech recognition, without even trying!

Dragon's in the air -- Is the market finally validated?

2007-11-20T03:34:00.000-08:00

For the last several mornings, we've noticed a rather well done commercial for Dragon Naturally Speaking's speech recognition software on major news networks, every morning in the AM.

The commercial shows an executive dictating a document, a lab tech finishing and sending an email and the executive's son starting, dictating & sending an IM. The commercial finishes up with statements such as "Windows Compatible"; "Talking is 3 times faster than typing"; "Up to 160 words a minute"; "Up to 99% accurate".

(It's also interesting that from a marketing viewpoint, this commercial shouts "simplicity" in every respect!).

In an interview with CNet News, when asked about why more light isn't shined on Windows' Vista's amazing speech recognition - Bill Gates talked about speech recognition migrating from being what many call an "obscure feature", into something more prominent:
"The speech recognition comes into it--all these things about natural interface are coming to the fore, and they are probably the thing that's most underestimated right now about the digital revolution" and "When voice recognition is used in the right way--let's say you're in the car and you want to pick somebody to call--that's improved very dramatically.."

Yes, it has! For those of us who have been using speech recognition for a decade or so, the differences are like comparing a wood stove to a microwave oven.

Although the website listed in the TV ad is a cheesy re-direct to a "Buy Right Now" ecommerce order page in Digital River, with absolutely no good copy to entice the curious should-I-buy-this seeker, nonetheless..

It seems to us, when a large, smart company like Nuance will plunk down the dollars necessary to have it's Dragon product ride the airwaves day after day, that's a pretty darn good indicator this part of the digital revolution is "ready for prime time!"

.

Macros are coming to Vista!

2007-11-19T20:03:00.000-08:00

.
Cool!

Rob Chambers, has just announced that Microsoft is releasing a Macro Tool, for Windows Vista in the near future.. a much anticipated, highly requested addition to the superb recognition that only Vista can offer.

You can read about it here.

Even cooler, the tool can be customized with XML, which can be a real snap.

Our hats are off, again, to the venerable Speech Components Group!

.

Wireless Speech Recognition in the ER

2007-11-15T20:53:00.000-08:00

An excellent speech recognition blog, (appropriately titled "Speech Recognition" :-) has posted a really interesting article about an intriguing remote-based wireless speech recognition system for Emergency Rooms, and also links to a terrific case study on the Crescendo site.

The case study's diagram outlines a system that uses a remote central voice & data server_+_Speech Recognition (SpeechMagic) Server that is accessed via Pocket PC's, and allows ER physicians to "walk and talk" while maintaining access and the physicians are provided with up-to-date patient data on their PDAs - any place, any time.. driven via speech commands.

It's fascinating reading, really worth checking out.
.

The "Light Link" for speech communications

2007-11-07T12:00:00.000-08:00

.
Laser communications systems are wireless connections that work similarly to fiber optic links, except the beam is transmitted through free space.

The U.S. government's new Lasercom Interoperability Standard has been tested by Boeing, and demonstrated to the Military Satellite Communications (MILSATCOM) user community that it can rely on a 10 to 40 gigabit per second TSAT backbone between satellites. Just imagine that kind of bandwidth ..

TSAT is designed to provide the secure, long-haul, high capacity backbone and full Internet-like functionality for U.S. forces to ensure that they have information superiority in any situation throughout the world.

The Japanese Experiment Module "Kibo" on the International Space Station, which can now attach to & interface with the ISS, will carry the 1st laser communications experiments based on TSAT technology. This experiment will demonstrate large-capacity, high-data-rate (2.5 Gbps) two-way communications, between the ISS and ground stations.

As to what that means: Real-time voice communication, among other things.
- Talk about "lightning fast" wireless remote speech recognition ..
Across how many miles .. ??

_________
Update
____

One of our readers left a comment that asked:
" ..surely the latency is the same as laser and radiowave both travel the distance at the same speed? "

We posed this question to our leading wireless audio engineer.

Here's what our engineer replied with:

"Light travels at 3e8 meters per second or 186282 miles per second.
The ISS orbits at (approx) 220 miles from Earth:
220/186282 = latency @ 0.0011 seconds each way. Light and radio travel at about the same speed thru space. The latency from the Moon to the Earth would be 1.3 seconds, each way, for example. The data rate does not really come into play unless you are compressing the data so much that your codec adds up to 100ms of extra delay.

Ultra Wideband at 60GHz can do a few Gbps - but only has a range of 20 feet or so. It really comes down to available bandwidth and transmit power, and power loss thru the medium you are transmitting through.."

The NASA sources we put this question to appear to base their position on throughput.

They note that RF's maximum throughput (presently) is around 100mbps, per 802.11n, where laser communications offer bandwidth to 2.56 terrabits per second (presently).

.

Bringing Harmony to Space

2007-11-07T10:20:00.000-08:00

At 1:01:15 PM ET today, space shuttle Discovery landed at NASA's Kennedy Space Center in Florida.

It was a fairly quiet mission media-wise, but it was one of the most important Space Shuttle missions in the history of the program.

Mission STS 120 carried something called the "Harmony Node 2" about which NASA says:

"Think of the next component set for delivery to the International Space Station as an international crossroads in space. That's the major function of the Italian-built U.S. module that will be ferried to the station aboard space shuttle Discovery during mission STS-120."

Harmony provides a passageway between three station science experiment facilities: the U.S. Destiny Laboratory, the Kibo Japanese Experiment Module, and the European Columbus Laboratory.

The international crossroads the Harmony 2 creates brings up to space something that, in the hardware world is a notable occasion. The European Columbus Labratory will now comfortably attach and exchange with the ISS; and NASA Engineers who tested the communications equipment of the Columbus said this, when finished:

“This is the best piece of hardware we have ever tested”.

… Wow! …

"Comparing Apples to Gold Nuggets"

2007-11-02T03:56:00.000-07:00

To quote Rob Chambers -

"The issue, as this author points out, is that people believe that the speech recognition in Apple's OS X can do far more than it actually can do. But, effectively, it can only do some limited command and control scenarios. Vista can do so much more. "

Comparing the speech recognition in Vista with speech recognition built into the Apple OS X is like comparing Apples to..
Well - the title says it all.

.